Skip to content

Deterministic max-pooling #106

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 1 commit into from
Jul 21, 2015
Merged

Deterministic max-pooling #106

merged 1 commit into from
Jul 21, 2015

Conversation

szagoruyko
Copy link
Member

This version is

  • Deterministic (according to @mys007)
  • Faster (close to cudnn)
  • Supports floor and ceil modes
  • Supports padW and padH
  • Uses 2 times less memory (stores only indexes, not x and y as before) as CPU version

(kernels borrowed from caffe)
CPU version is here torch/nn#309, both PRs are cross-reviewed by me and @fmassa

@fmassa
Copy link
Contributor

fmassa commented Jul 10, 2015

BTW, this PR also fixes #53 (for SpatialMaxPooling)

@szagoruyko szagoruyko mentioned this pull request Jul 16, 2015
Closed
soumith added a commit that referenced this pull request Jul 21, 2015
@soumith
Merge pull request #106 from szagoruyko/master
0ae8ed8 
Deterministic max-pooling
@soumith soumith merged commit 0ae8ed8 into torch:master Jul 21, 2015
@soumith
Copy link
Member

soumith commented Jul 21, 2015

thanks a lot!

This was referenced Jul 21, 2015
Merged
Merged
@albanD albanD mentioned this pull request Jul 23, 2015
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@szagoruyko @fmassa @soumith